Online visual tracking with histograms and articulating blocks

S. M.Shahed Nejhum, Jeffrey Ho, Ming Hsuan Yang

Research output: Contribution to journalArticle

56 Citations (Scopus)

Abstract

We propose an algorithm for accurate tracking of articulated objects using online update of appearance and shape. The challenge here is to model foreground appearance with histograms in a way that is both efficient and accurate. In this algorithm, the constantly changing foreground shape is modeled as a small number of rectangular blocks, whose positions within the tracking window are adaptively determined. Under the general assumption of stationary foreground appearance, we show that robust object tracking is possible by adaptively adjusting the locations of these blocks. Implemented in MATLAB without substantial optimization, our tracker runs already at 3.7 frames per second on a 3 GHz machine. Experimental results have demonstrated that the algorithm is able to efficiently track articulated objects undergoing large variation in appearance and shape.

Original languageEnglish
Pages (from-to)901-914
Number of pages14
JournalComputer Vision and Image Understanding
Volume114
Issue number8
DOIs
Publication statusPublished - 2010 Aug 1

Fingerprint

MATLAB

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Nejhum, S. M.Shahed ; Ho, Jeffrey ; Yang, Ming Hsuan. / Online visual tracking with histograms and articulating blocks. In: Computer Vision and Image Understanding. 2010 ; Vol. 114, No. 8. pp. 901-914.
@article{e664e2524d9c46b8bab751134597754e,
title = "Online visual tracking with histograms and articulating blocks",
abstract = "We propose an algorithm for accurate tracking of articulated objects using online update of appearance and shape. The challenge here is to model foreground appearance with histograms in a way that is both efficient and accurate. In this algorithm, the constantly changing foreground shape is modeled as a small number of rectangular blocks, whose positions within the tracking window are adaptively determined. Under the general assumption of stationary foreground appearance, we show that robust object tracking is possible by adaptively adjusting the locations of these blocks. Implemented in MATLAB without substantial optimization, our tracker runs already at 3.7 frames per second on a 3 GHz machine. Experimental results have demonstrated that the algorithm is able to efficiently track articulated objects undergoing large variation in appearance and shape.",
author = "Nejhum, {S. M.Shahed} and Jeffrey Ho and Yang, {Ming Hsuan}",
year = "2010",
month = "8",
day = "1",
doi = "10.1016/j.cviu.2010.04.002",
language = "English",
volume = "114",
pages = "901--914",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",
number = "8",

}

Online visual tracking with histograms and articulating blocks. / Nejhum, S. M.Shahed; Ho, Jeffrey; Yang, Ming Hsuan.

In: Computer Vision and Image Understanding, Vol. 114, No. 8, 01.08.2010, p. 901-914.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online visual tracking with histograms and articulating blocks

AU - Nejhum, S. M.Shahed

AU - Ho, Jeffrey

AU - Yang, Ming Hsuan

PY - 2010/8/1

Y1 - 2010/8/1

N2 - We propose an algorithm for accurate tracking of articulated objects using online update of appearance and shape. The challenge here is to model foreground appearance with histograms in a way that is both efficient and accurate. In this algorithm, the constantly changing foreground shape is modeled as a small number of rectangular blocks, whose positions within the tracking window are adaptively determined. Under the general assumption of stationary foreground appearance, we show that robust object tracking is possible by adaptively adjusting the locations of these blocks. Implemented in MATLAB without substantial optimization, our tracker runs already at 3.7 frames per second on a 3 GHz machine. Experimental results have demonstrated that the algorithm is able to efficiently track articulated objects undergoing large variation in appearance and shape.

AB - We propose an algorithm for accurate tracking of articulated objects using online update of appearance and shape. The challenge here is to model foreground appearance with histograms in a way that is both efficient and accurate. In this algorithm, the constantly changing foreground shape is modeled as a small number of rectangular blocks, whose positions within the tracking window are adaptively determined. Under the general assumption of stationary foreground appearance, we show that robust object tracking is possible by adaptively adjusting the locations of these blocks. Implemented in MATLAB without substantial optimization, our tracker runs already at 3.7 frames per second on a 3 GHz machine. Experimental results have demonstrated that the algorithm is able to efficiently track articulated objects undergoing large variation in appearance and shape.

UR - http://www.scopus.com/inward/record.url?scp=77953961587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953961587&partnerID=8YFLogxK

U2 - 10.1016/j.cviu.2010.04.002

DO - 10.1016/j.cviu.2010.04.002

M3 - Article

AN - SCOPUS:77953961587

VL - 114

SP - 901

EP - 914

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

IS - 8

ER -